Borrowing it
Nothing to install: this file belongs to Montimage/mitre-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Montimage/mitre-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/Montimage/mitre-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/montimage/mitre-mcp/agents-md)<a href="https://agentmods.dev/instructions/montimage/mitre-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/montimage/mitre-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/montimage/mitre-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/montimage/mitre-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00815 | $0.00815 |
| Opus 5.5 | $0.00326 | $0.00326 |
| Sonnet 5.5 | $0.00163 | $0.00163 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
mitre-mcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Cross-agent rules for this repository. The recorded build, test, and install commands are pinned once in CLAUDE.md under ## Commands; the complete environment-variable inventory lives in CONTRIBUTING.md under ## Agent-runnable environment.
Project
MITRE ATT&CK MCP server: Python package mitre_mcp (requires Python >= 3.11) plus a React/Vite frontend in frontend/ (Node 24). Invariants: never change observed MITRE tool outputs, keep the model dropdown in sync with the manifests, and never commit generated data or secrets.
Commands
Run the commands of record verbatim from CLAUDE.md ## Commands — they are defined there once and referenced here rather than duplicated. For setup details and environment variable names, see CONTRIBUTING.md ## Agent-runnable environment.
Layout
mitre_mcp/— server package:mitre_mcp_server.pythin entry point and public re-export surface;data.pydownload/cache/indices,models.pyresult schemas,server.pythemcpobject + lifespan,tools.pythe nine tools,cli.pyargv/banner/signals,http.pytransport security + ASGI app,config.pyenv-driven config,validators.pytests/— pytest suite;tests/integration/needs a committed STIX fixturefrontend/— React/Vite chat UI with its own lint and build pipelineclients/— Python and Node.js sample clientsscripts/— installer and ATT&CK data download helpersdata/— git-ignored ATT&CK cache; never commit it
Conventions
- Minimal, focused diffs; conventional commits
type(scope): description (#N). - Branch prefix follows the issue type:
fix/,feat/,refactor/,docs/,test/,chore/. - The recorded commands may still be RED — restoring green is P0 work; a red baseline is not your regression.
Constraints
- Repository etiquette — never commit or push without being asked, never add
Co-Authored-Bytrailers — is pinned inCLAUDE.md## Constraintsand applies to every agent. - Never copy secret values out of
.envor the.mcpregistry_*tokenfiles — environment variable names only. - Never commit
tests/data/ordata/contents — both are git-ignored by design.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 59 lines · 815 tokens per session scan A 97ac98bf71d4
mitre-mcp AGENTS.md is an instructions file published in the GitHub repository Montimage/mitre-mcp (15 stars, last pushed 11d ago), licensed MIT. It adds 815 tokens to every session, about $0.0033 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-19.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.